Poisson2Gaussian: Noise Gaussianization to Enhance Image Denoising
For practitioners in photography, microscopy, and astronomy, P2G provides an architecture-agnostic method to improve denoising performance without requiring paired clean data or explicit noise parameters.
The paper proposes Poisson2Gaussian (P2G), a noise Gaussianization method that converts complex real-world noise to i.i.d. Gaussian noise via probability density matching, enabling existing denoisers to perform better. P2G achieves state-of-the-art performance across diverse datasets, with up to 0.75 dB PSNR improvement in challenging scenarios.
The quantum nature of light determines the inherent Poisson stochasticity of photon detection, which is ubiquitous in photography, microscopy, and astronomy. However, our controlled numerical studies reveal that the signal-dependency, heteroscedasticity, and statistical asymmetry of Poisson-mixed noise make it challenging for existing denoisers to learn. In contrast, i.i.d. Gaussian noise, with its statistical independence and symmetric distribution, is easier to model for networks. To address this gap, we propose Poisson2Gaussian (P2G), a noise Gaussianization method that explicitly converts complex real-world noise to i.i.d. Gaussian noise via probability density matching beyond low-order moments. We also design an unbiased denoising framework that synergizes P2G with downstream denoisers, ensuring convergence to the underlying signal without requiring paired clean data or explicit noise parameters. Extensive experiments demonstrate that P2G consistently achieves state-of-the-art performance across diverse datasets. In challenging scenarios where noise strongly deviates from Gaussian statistics, our method improves the PSNR by up to 0.75 dB. Notably, P2G is architecture-agnostic and can provide universal improvements for various denoisers. The source code will be publicly available.